Wikitopia
ExLlamaV2
productInference Engine
Try in Playground →RSS
Overview
Developed byturboderp
LicenseMIT License
Open source✓ Open Source
Use caseLLM inference engine with quantization support
Technical
Protocols
EXL2 quantization format
Integrates with
text-generation-webui
Also see
Alternative to
llama.cpp
Based onExLlama
Knowledge graph stats
Claims11
Avg confidence93%
Avg freshness100%
Last updatedUpdated 1h ago
Trust distribution
100% unverified
Governance
EU Risknot classified
Training data disclosure →

ExLlamaV2

product

Fast inference library for Llama models with support for various quantization methods and GPU acceleration.

Compare with...

open source

ValueTrustConfidenceFreshnessSources
true○UnverifiedHighFresh1

pricing model

ValueTrustConfidenceFreshnessSources
free○UnverifiedHighFresh1

supports model

ValueTrustConfidenceFreshnessSources
Llama models○UnverifiedHighFresh1

primary use case

ValueTrustConfidenceFreshnessSources
LLM inference engine with quantization support○UnverifiedHighFresh1

developed by

ValueTrustConfidenceFreshnessSources
turboderp○UnverifiedHighFresh1

supports protocol

ValueTrustConfidenceFreshnessSources
EXL2 quantization format○UnverifiedHighFresh1

license type

ValueTrustConfidenceFreshnessSources
MIT License○UnverifiedHighFresh1

requires

ValueTrustConfidenceFreshnessSources
CUDA GPU○UnverifiedHighFresh1

based on

ValueTrustConfidenceFreshnessSources
ExLlama○UnverifiedModerateFresh1

integrates with

ValueTrustConfidenceFreshnessSources
text-generation-webui○UnverifiedModerateFresh1

alternative to

ValueTrustConfidenceFreshnessSources
llama.cpp○UnverifiedModerateFresh1

Alternatives & Similar Tools

llama.cpp
alternative to
Compare →

Commonly Used With

text-generation-webui

Related entities

Claim count: 11Last updated: 4/11/2026Edit history